Media · Local MCP server
Whisper Transcribe
Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.ZahiriNatZuke/whisper-transcribe-mcp- Version
- 1.1.3
- Status
- Active
- Category
- media
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-09-22
- Updated
- 2026-09-22
- Publisher
- ZahiriNatZuke (GitHub) · 2 servers with pages here
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/ZahiriNatZuke) · how
- Listed under
- OpenAI MCP servers, Whisper MCP servers
- Website
- github.com/ZahiriNatZuke/whisper-transcribe-mcp
- Repository
- github.com/ZahiriNatZuke/whisper-transcribe-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: uvx | whisper-transcribe-mcp | 1.1.3 | stdio |
How to connect Whisper Transcribe
Whisper Transcribe runs locally from a Python package published to PyPI: whisper-transcribe-mcp version 1.1.3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx whisper-transcribe-mcp. It reads these environment variables: OPENAI_API_KEY (secret), WHISPER_MODEL and WHISPER_POST_PROCESS_MODEL; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"whisper-transcribe-mcp": {
"command": "uvx",
"args": [
"whisper-transcribe-mcp"
],
"env": {
"OPENAI_API_KEY": "<secret>",
"WHISPER_MODEL": "<value>",
"WHISPER_POST_PROCESS_MODEL": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from ZahiriNatZuke (GitHub)
| Server | Runs |
|---|---|
| Local DelegateDelegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota. | Local · stdio |
More media servers
| Server | Runs |
|---|---|
| What's NewChangelogs for apps, games and operating systems. Ask what shipped since the version you run. | Remote · HTTPLive check: ✓ handshake |
| Whichli · Photo PollsTurn photos or product links into a poll your friends vote on. One link, free, no account needed. | Remote · HTTPLive check: ✓ handshake |
| Whipscribe MCPTranscribe audio/video files or URLs via the WhipScribe cloud API and fetch the transcript. | Local · stdio |
| Whisper MCPLocal audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models. | Local · stdio |
| WindowsForum MCP ServerSearch WindowsForum.com threads, posts, and Windows news; fetch documents and Microsoft KB info. | Remote · HTTPLive check: ✓ handshake |
| Wisp MCPWisp Panel MCP server for secure game server management through the Wisp Client API. | Local · stdio |
| Wokelo MCP ServerCompany and market intelligence, news, enrichment, and agentic workflows for dealmakers. | Remote · HTTPLive check: ✗ no handshake |
| WoopSocial Social Media MCPPost to social media (Facebook, Instagram, LinkedIn, Pinterest, YouTube, TikTok, X/Twitter and more) | Remote · HTTPLive check: sign-in required |